• Shubham Agale
• Vishal Mane
• Adinath Gonjare
• Ashutosh Rode

In this paper, a novel deep neural network (DNN) architecture is proposed to generate the speech features of both the target speaker and interfere for speech separation. DNN is adopted here to directly model the highly nonlinear relationship between speech features of the mixed signals and the two competing speakers. With the modified output speech features for learning the parameters of the DNN, the generalization capacity to unseen interferes is improved for separating the target speech. Meanwhile, without any prior information from the interfere, the interfering speech can also be separated. Experimental results show that the proposed new DNN enhances the separation performance in terms of different objective measures under the semi- supervised mode where the training data of the target speaker is provided while the unseen interfere in the separation stage is predicted by using multiple interfering speakers mixed with the target speakers mixed with the target speaker in the training state.

Speech separation, deep neural network

"Speech Separation using Python", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 1, page no.b117-b120, January-2022, Available :http://www.jetir.org/papers/JETIR2201116.pdf

"Speech Separation using Python", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 1, page no. ppb117-b120, January-2022, Available at : http://www.jetir.org/papers/JETIR2201116.pdf